The Average layer that comes with Keras already has support for masking, however, looking at the source code of Average Layer, it is not clear to me how and if the masking is applied.
I have a list of inputs, each with its own masking (coming from an embedding layer, for example). The average layer I want should take the average of those inputs that have not been masked. In other words, if an input is masked, it should not have any say in the calculated mean. If all the inputs are masked, then the output is masked and passed along to the next layers.
A related question is, the Average Layer that comes with the library only supports merge functions of a list of inputs. Is there library support for merging a tensor along a particular dimension? Is it possible to slice a tensor into a list of inputs to feed into the average layer? If not, how to take the average of tensor along some dimension in presence of masking?
I am inclining towards writing a custom average layer that computes the masks and consume the masks in calculating the output, but from the documentation, it is not clear how to do so?
Any pointers or code samples is highly appreciated.
If you look at the source code of the Average layer, it actually subclass from the "_Merge" layer, since Average layer doesn't overwrite the "compute_mask" function, so it will inherit the "compute_mask" function of "_Merge" layer, which is as follows:
def compute_mask(self, inputs, mask=None):
if mask is None:
return None
if not isinstance(mask, list):
raise ValueError('`mask` should be a list.')
if not isinstance(inputs, list):
raise ValueError('`inputs` should be a list.')
if len(mask) != len(inputs):
raise ValueError('The lists `inputs` and `mask` '
'should have the same length.')
if all(m is None for m in mask):
return None
masks = [array_ops.expand_dims(m, axis=0) for m in mask if m is not None]
return K.all(K.concatenate(masks, axis=0), axis=0, keepdims=False)
The last 4 lines say that: if all the input masks are None, then return None. Otherwise the output mask is first concatenating all the masks that are not None, then do a "all" operation, which means the resulted mask is masked (False) if one of the input_mask is masked (False), and the resulted mask is True (not masked) only if all the input_masks are not masked (True).
Related
In all code examples for keras I see that the input shape is passed directly and it is surmised that the batch size is the first one , eg:
model = Sequential()
model.add(Dense(32, input_shape=(16,)))
# now the model will take as input arrays of shape (*, 16)
# and output arrays of shape (*, 32)
However when it comes to custom losses I see that the last axis (axis=-1) is used.
def loss(y_true,y_pred):
return K.mean(K.square(y_pred - y_true), axis=-1)
When writing the loss should one think of y_true and y_pred as batches or singular samples?
I'm assuming it's the former , but if that's the case I can't understand why it's specifying the last axis
In your custom loss function, you treat y_true and y_pred as batches which is also the case for the returned value of the function. If you only calculate one loss for your network, you could also get rid of the specified axis, since you only want a single value for your loss in the end.
But if you have multiple outputs in your network and you want to calculate the total loss, where each output might use its own loss functions, things begin to change.
Please check out: https://github.com/keras-team/keras/blob/master/keras/engine/training.py#L658
where the function to calculate the total loss, _prepare_total_loss, is called.
In this function, the following code is executed:
output_loss = loss_fn(y_true, y_pred, sample_weight=sample_weight)
which returns the loss for a single output of your network. This is also where your custom loss function gets called. If there are multiple outputs, all of them are calculated, weighted and added to the total loss: total_loss += loss_weight * output_loss
In the end, _prepare_total_loss returns K.mean(total_loss). So in the simplest case, if your custom loss function returned a vector with its length equal to the batch size, and there is only one output with loss in your network, the final loss will be the mean of the output-vector returned by your custom loss.
But in case of multiple outputs and multiple losses, you first want to calculate the loss vector of a batch for each output and therefore loss function, take their weighted sum and then calculate the final loss by taking the mean of the resulting vector.
If your loss functions would return a single loss value each instead of a batch-sized vector, the final loss would be the mean of multiple mean loss values which differs from the mean loss of the whole batch.
I have a question about the use of the sample_weight parameter in the context of data augmentation in Keras with the ImageDataGenerator. Let's say I have a series of simple images with just one class of objects. So, for each image, I will have a corresponding mask with pixels = 0 for the background and 1 for where the object is labeled.
However, this dataset is unbalanced because a significant amount of these images are empty, which mean with masks just containing 0.
If I understood well, the 'sample_weight' parameter of the flow method of ImageDataGenerator is here to put the focus on the the samples of my dataset that I find more interesting, i.e. where my object is present.
My question is: what is the concrete influence of this sample_weight parameter on the training of my model. Does it influence the data augmentation? If I use the 'validation_split' parameter, does it influence the way validation sets are generated?
Here is the part of my code my question refers to:
data_gen_args = dict(rotation_range=90,
width_shift_range=0.4,
height_shift_range=0.4,
zoom_range=0.4,
horizontal_flip=True,
fill_mode='reflect',
rescale=1. / 255,
validation_split=0.2,
data_format='channels_last'
)
image_datagen = ImageDataGenerator(**data_gen_args)
imf = image_datagen.flow(
x=stacked_images_channel,
y=stacked_masks_channel,
batch_size=batch_size,
shuffle=False,
seed=seed,subset='training',
sample_weight = sample_weight,
save_to_dir = 'traindir',
save_prefix = 'train_'
)
valf = image_datagen.flow(
x=stacked_images_channel,
y=stacked_masks_channel,
batch_size=batch_size,
shuffle=False,
seed=seed,subset='validation',
sample_weight = sample_weight,
save_to_dir = 'valdir',
save_prefix = 'val_'
)
STEP_SIZE_TRAIN=imf.n//imf.batch_size
STEP_SIZE_VALID=valf.n//valf.batch_size
model = unet.UNet2(numberOfClasses, imshape, '', learningRate, depth=4)
history = model.fit_generator(generator=imf,
steps_per_epoch=STEP_SIZE_TRAIN,
epochs=epochs,
validation_data=valf,
validation_steps=STEP_SIZE_VALID,
verbose=2
)
Thank you in advance for your attention.
As for Keras 2.2.5 with preprocessing at 1.1.0, the sample_weight is passed along with the samples and applied during processing. When calling .fit_generator, the model is trained on batches, each batch using sample weights:
model.train_on_batch(x, y,
sample_weight=sample_weight,
class_weight=class_weight)
In the source code of .train_on_batch, the documentation states: "sample_weight: Optional array of the same length as x, containing weights to apply to the model's loss for each sample. (...)". The actual application of weights happens when calculating loss on each batch. When compiling a model, Keras generates a "weighted loss" function out of the desired loss function. The weighted computation is stated in the code as:
def weighted(y_true, y_pred, weights, mask=None):
"""Wrapper function.
# Arguments
y_true: `y_true` argument of `fn`.
y_pred: `y_pred` argument of `fn`.
weights: Weights tensor.
mask: Mask tensor.
# Returns
Scalar tensor.
"""
# score_array has ndim >= 2
score_array = fn(y_true, y_pred)
if mask is not None:
# Cast the mask to floatX to avoid float64 upcasting in Theano
mask = K.cast(mask, K.floatx())
# mask should have the same shape as score_array
score_array *= mask
# the loss per batch should be proportional
# to the number of unmasked samples.
score_array /= K.mean(mask) + K.epsilon()
# apply sample weighting
if weights is not None:
# reduce score_array to same ndim as weight array
ndim = K.ndim(score_array)
weight_ndim = K.ndim(weights)
score_array = K.mean(score_array,
axis=list(range(weight_ndim, ndim)))
score_array *= weights
score_array /= K.mean(K.cast(K.not_equal(weights, 0), K.floatx()))
return K.mean(score_array)
This wrapper shows it first calculates the desired loss (call to fn(y_true, y_pred)), then applies weighing if weights where passed (either with sample_weight or class_weight).
With this context in mind:
what is the concrete influence of this sample_weight parameter on the training of my model.
Weights are basically multiplied to the loss (and normalized). So "heavy" weights (more than 1) samples cause more loss, so larger gradients. "Light" weights reduce the importance of the sample and lead to smaller gradients.
Does it influence the data augmentation?
It depends on what you mean. Here is what I can say from experience, where I perform augmentation before feeding a Keras data generator (doing so as there were issues in preprocessing, as far as I know still existing in Preprocessing 1.1.0):
When feeding already augmented data to the generator, the .flow call will require a sample weights list as long as the input data. So the influence of weighing on augmentation depends on how the weights are chosen. A data point augmented N times may assign the same weight to each augmentation, or 1/N depending on the intent.
The default behaviour in Keras seems to assign the same weight to each augmentation (transform) performed by Keras. The code looks pretty clear, although I have never relied on it.
If I use the 'validation_split' parameter, does it influence the way validation sets are generated?
The sample_weight parameter does not seem to interfere with validation_split. I have not looked into the code specifically, but splitting basically gets the input data, and keeps a split for validation---whatever the data is. When sample_weight is added, what changes is each data point: Without weight, data is (x, y); with weight, data becomes (x, y, weight).
I have to train a network on unlabelled data of binary type (True/False), which sounds like unsupervised learning. This is what the normalised data look like:
array([[-0.05744527, -1.03575495, -0.1940105 , -1.15348956, -0.62664491,
-0.98484037],
[-0.05497629, -0.50935675, -0.19396862, -0.68990988, -0.10551919,
-0.72375012],
[-0.03275552, 0.31480204, -0.1834951 , 0.23724946, 0.15504367,
0.29810553],
...,
[-0.05744527, -0.68482282, -0.1940105 , -0.87534175, -0.23580062,
-0.98484037],
[-0.05744527, -1.50366446, -0.1940105 , -1.52435329, -1.14777063,
-0.98484037],
[-0.05744527, -1.26970971, -0.1940105 , -1.33892142, -0.88720777,
-0.98484037]])
However, I do have a constraint on the total number of True labels in my data. This doesn't mean I can build a classical custom loss function in Keras taking (y_true, y_pred) arguments as required: my external constraint is just on the predicted total of True and False, not on the individual labels.
My question is whether there is a somewhat "standard" approach to this kind of problems, and how that is implementable in Keras.
POSSIBLE SOLUTION
Should I assign y_true randomly as 0/1, have a network return y_pred as 1/0 with a sigmoid activation function, and then define my loss function as
sum_y_true = 500 # arbitrary constant known a priori
def loss_function(y_true, y_pred):
loss = np.abs(y_pred.sum() - sum_y_true)
return loss
In the end, I went with the following solution, which worked.
1) Define batches in your dataframe df with a batch_id column, so that in each batch Y_train is your identical "batch ground truth" (in my case, the total number of True labels in the batch). You can then pass these instances together to the network. This can be done with a generator:
def grouper(g,x,y):
while True:
for gr in g.unique():
# this assigns indices to the entire set of values in g,
# then subsects to all the rows in which g == gr
indices = g == gr
yield (x[indices],y[indices])
# train set
train_generator = grouper(df.loc[df['set'] == 'train','batch_id'], X_train, Y_train)
# validation set
val_generator = grouper(df.loc[df['set'] == 'val','batch_id'], X_val, Y_val)
2) define a custom loss function, to track how close the total number of instances predicted as true matches the ground truth:
def custom_delta(y_true, y_pred):
loss = K.abs(K.mean(y_true) - K.sum(y_pred))
return loss
def custom_wrapper():
def custom_loss_function(y_true, y_pred):
return custom_delta(y_true, y_pred)
return custom_loss_function
Note that here
a) Each y_true label is already the sum of the ground truth in our batch (cause we don't have individual values). That's why y_true is not summed over;
b) K.mean is actually a bit of an overkill to extract a single scalar from this uniform tensor, in which all y_true values in each batch are identical - K.min or K.max would also work, but I haven't tested whether their performance is faster.
3) Use fit_generator instead of fit:
fmodel = Sequential()
# ...your layers...
# Create the loss function object using the wrapper function above
loss_ = custom_wrapper()
fmodel.compile(loss=loss_, optimizer='adam')
history1 = fmodel.fit_generator(train_generator, steps_per_epoch=total_batches,
validation_data=val_generator,
validation_steps=df.loc[encs.df['set'] == 'val','batch_id'].nunique(),
epochs=20, verbose = 2)
This way the problem is basically addressed as one of supervised learning, although without individual labels, which means that notions like true/false positive are meaningless here.
This approach not only managed to give me a y_pred that closely matches the totals I know per batch. It actually finds two groups (True/False) that occupy the expected different portions of parameter space.
In keras, I want to calculate the mean of nonzero embedding output.
I wonder what is the difference between mask_zero=True or False in Embedding Layer.
I tried the code below :
input_data = Input(shape=(5,), dtype='int32', name='input')
embedding_layer = Embedding(1000, 24, input_length=5,mask_zero=True,name='embedding')
out = word_embedding_layer(input_data)
def antirectifier(x):
x = K.mean(x, axis=1, keepdims=True)
return x
def antirectifier_output_shape(input_shape):
shape = list(input_shape)
return tuple(shape)
out = Lambda(antirectifier, output_shape=antirectifier_output_shape,name='lambda')(out)
But it seems that the result is the mean of all the elements, how can i just calculate the mean of all nonzero inputs?
From the function's doc :
If this is True then all subsequent layers in the model need to
support masking
Your lambda function doesn't support masking. For example Recurrent layers in Keras support masking. If you set mask_zero=True in your embeddings, then all the 0 indices that you feed to the embedding layer will be propagated as "masked" and the following layers that are able to understand the "masked" information will use them.
Basically, if you build a "mean" layer that grabs the mask and computes the average only for non-masked values, then you will get the desired results.
You can find here a way to build your lambda layers that support masking
I hope it helps.
Keras documentation isn't clear what this actually is. I understand we can use this to compress the input feature space into a smaller one. But how is this done from a neural design perspective? Is it an autoenocder, RBM?
As far as I know, the Embedding layer is a simple matrix multiplication that transforms words into their corresponding word embeddings.
The weights of the Embedding layer are of the shape (vocabulary_size, embedding_dimension). For each training sample, its input are integers, which represent certain words. The integers are in the range of the vocabulary size. The Embedding layer transforms each integer i into the ith line of the embedding weights matrix.
In order to quickly do this as a matrix multiplication, the input integers are not stored as a list of integers but as a one-hot matrix. Therefore the input shape is (nb_words, vocabulary_size) with one non-zero value per line. If you multiply this by the embedding weights, you get the output in the shape
(nb_words, vocab_size) x (vocab_size, embedding_dim) = (nb_words, embedding_dim)
So with a simple matrix multiplication you transform all the words in a sample into the corresponding word embeddings.
The Keras Embedding layer is not performing any matrix multiplication but it only:
1. creates a weight matrix of (vocabulary_size)x(embedding_dimension) dimensions
2. indexes this weight matrix
It is always useful to have a look at the source code to understand what a class does. In this case, we will have a look at the class Embedding which inherits from the base layer class called Layer.
(1) - Creating a weight matrix of (vocabulary_size)x(embedding_dimension) dimensions:
This is occuring at the build function of Embedding:
def build(self, input_shape):
self.embeddings = self.add_weight(
shape=(self.input_dim, self.output_dim),
initializer=self.embeddings_initializer,
name='embeddings',
regularizer=self.embeddings_regularizer,
constraint=self.embeddings_constraint,
dtype=self.dtype)
self.built = True
If you have a look at the base class Layer you will see that the function add_weight above simply creates a matrix of trainable weights (in this case of (vocabulary_size)x(embedding_dimension) dimensions):
def add_weight(self,
name,
shape,
dtype=None,
initializer=None,
regularizer=None,
trainable=True,
constraint=None):
"""Adds a weight variable to the layer.
# Arguments
name: String, the name for the weight variable.
shape: The shape tuple of the weight.
dtype: The dtype of the weight.
initializer: An Initializer instance (callable).
regularizer: An optional Regularizer instance.
trainable: A boolean, whether the weight should
be trained via backprop or not (assuming
that the layer itself is also trainable).
constraint: An optional Constraint instance.
# Returns
The created weight variable.
"""
initializer = initializers.get(initializer)
if dtype is None:
dtype = K.floatx()
weight = K.variable(initializer(shape),
dtype=dtype,
name=name,
constraint=constraint)
if regularizer is not None:
with K.name_scope('weight_regularizer'):
self.add_loss(regularizer(weight))
if trainable:
self._trainable_weights.append(weight)
else:
self._non_trainable_weights.append(weight)
return weight
(2) - Indexing this weight matrix
This is occuring at the call function of Embedding:
def call(self, inputs):
if K.dtype(inputs) != 'int32':
inputs = K.cast(inputs, 'int32')
out = K.gather(self.embeddings, inputs)
return out
This functions returns the output of the Embedding layer which is K.gather(self.embeddings, inputs). What tf.keras.backend.gather exactly does is to index the weights matrix self.embeddings (see build function above) according to the inputs which should be lists of positive integers.
These lists can be retrieved for example if you pass your text/words inputs to the one_hot function of Keras which encodes a text into a list of word indexes of size n (this is NOT one hot encoding - see also this example for more info: https://machinelearningmastery.com/use-word-embedding-layers-deep-learning-keras/).
Therefore, that's all. There is no matrix multiplication.
On the contrary, the Keras Embedding layer is only useful because exactly it avoids performing a matrix multiplication and hence it economizes on some computational resources.
Otherwise, you could just use a Keras Dense layer (after you have encoded your input data) to get a matrix of trainable weights (of (vocabulary_size)x(embedding_dimension) dimensions) and then simply do the multiplication to get the output which will be exactly the same with the output of the Embedding layer.
In Keras, the Embedding layer is NOT a simple matrix multiplication layer, but a look-up table layer (see call function below or the original definition).
def call(self, inputs):
if K.dtype(inputs) != 'int32':
inputs = K.cast(inputs, 'int32')
out = K.gather(self.embeddings, inputs)
return out
What it does is to map each a known integer n in inputs to a trainable feature vector W[n], whose dimension is the so-called embedded feature length.
In simple words (from the functionality point of view), it is a one-hot encoder and fully-connected layer. The layer weights are trainable.